k-means and k-medoids clustering merged conceptually distinct mechanistic reasoning types, making them less effective than HDBSCAN for this data¶

Claim · All claims
Evidence · 1 study · associational r1 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? k-means and k-medoids clustering merged conceptually distinct mechanistic reasoning types into the same clusters and were less effective than HDBSCAN at revealing nuanced differences in students' reasoning. → Martin 2025

Evidence¶

Martin 2025¶

Martin, P. P., Kranz, D., & Graulich, N. (2025). Revealing Rubric Relations: Investigating the Interdependence of a Research-Informed and a Machine Learning-Based Rubric in Assessing Student Reasoning in Chemistry. International Journal of Artificial Intelligence in Education, 35, 1465–1503. https://doi.org/10.1007/s40593-024-00440-y

q2 · i? · associational · r1

Algorithm comparison reported in the ML-Based Rubric methods section: the authors applied k-means and k-medoids alongside HDBSCAN and found they "merged conceptually distinct mechanistic reasoning types into the same clusters", based on qualitative evaluation of the solutions.

"These algorithms merged conceptually distinct mechanistic reasoning types into the same clusters, so these algorithms were less effective in revealing nuanced differences in students' reasoning about reaction mechanisms."

Discussion¶

Related Claims¶

• HDBSCAN clustering of BERT embeddings yielded fifteen clusters capturing the content and complexity of students' mechanistic reasoning — related
• Research-informed and ML-based rubrics assess students' mechanistic reasoning comparably, supporting ML techniques in rubric development — related